Abstract
BACKGROUND: Analyzing distractor qualities of a pediatrics subject test in a national-level examination is vital in developing high-quality items for the discipline. Yet traditional approaches focus on key answers only and therefore are less informative. The number of distractors can also be parsimonized to improve the item development. MATERIALS AND METHODS: From a pediatrics subject test at the national level, raw responses of 44,332 examines to nineteen multiple-choice questions were analyzed, such that the distractor qualities were evaluated via traditional and advanced methods such as canonical correlation index. Additionally, a simulation study was conducted to investigate the impact of eliminating distractor numbers on reliability. RESULTS: The traditional item analysis showed that most items had acceptable psychometric properties, and two items were flagged for low item difficulty and discrimination. Distractor analysis showed that about one-third of items had poorly functioning distractors based on relatively a low choice frequency (<5%) and a small effect size of distractor discrimination. The simulation study also confirmed that shrinking distractor numbers to 4 was viable. CONCLUSIONS: Integrating multiple methods, especially the advanced ones, provides comprehensive evaluations of the item quality. Simulations can help re-consider the decision to set distractor numbers for cost-effectiveness. These proposed methods can improve further development of the pediatrics subject test.